Chest Audio Monitoring via Signal Decomposition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current monitoring systems for respiratory and cardiac parameters face challenges such as low signal-to-noise ratio, variable breathing patterns, interference from non-biological and biological sounds, and the need for bulky and visible medical equipment, making continuous monitoring in real-world settings difficult.
Innovation Solution
A monitoring system that uses a data-driven decomposition technique on time-series features from chest audio signals, employing singular spectral analysis or empirical mode decomposition to decompose detection signals into physiological and noise components, allowing for indirect monitoring of respiratory and cardiac variables, and is designed to be unobtrusive and compatible with daily devices like smartphones.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional monitoring systems use bulky medical equipment, then measurement precision is improved, but ease of operation deteriorates due to patient discomfort and low compliance
Solution Approach 1:
The patent replaces traditional mechanical/stethoscope-based monitoring systems with acoustic sensor technology that captures chest sounds electronically. This substitution enables the system to be integrated into lightweight, wearable devices or smartphones, eliminating the need for bulky medical equipment while maintaining monitoring accuracy through digital signal processing and decomposition algorithms.
2Ease of operation
If acoustic signals are used for monitoring, then ease of operation is improved through unobtrusive sensing, but measurement precision deteriorates due to low signal-to-noise ratio and interference
Solution Approach 1:
The patent applies signal decomposition techniques that segment the acoustic signal into distinct physiological components (respiratory sounds, cardiac sounds) and noise components. By separating these elements mathematically, the system can extract clean physiological information from the mixed acoustic signal, thereby improving measurement precision while maintaining unobtrusive monitoring capabilities.
Solution Approach 2:
The patent introduces signal processing algorithms and decomposition methods as intermediary layers between the acoustic sensor and the physiological parameter extraction. These intermediaries filter out noise and interference, transforming the low-quality raw acoustic signal into high-quality physiological data, thus resolving the signal-to-noise ratio problem.
3Measurement precision
If signal processing filters are applied to improve measurement precision, then measurement precision is improved, but device complexity increases requiring re-design for different conditions
Solution Approach 1:
The patent employs dynamic signal decomposition methods that automatically adapt to varying respiratory patterns and breathing conditions. Rather than using fixed filters that require re-design for different conditions, the decomposition algorithm dynamically adjusts to extract physiological signals from diverse breathing patterns, including variable respiratory rates and abnormal patterns, thereby reducing device complexity while maintaining precision.
Data Source
AI summary
The present invention relates to a system (100) and method (800) capable of indirectly monitoring respiratory and cardiac variables. A decomposition technique on time-series of features extracted from the chest audio signal α(t) is proposed. The proposed monitoring system (100) may acquire the acoustic signal on the chest of a subject (140) by means of a wearable transducer (150). The proposed system may estimate a number of physiological variables such as flow estimates, respiration rate, inspiration and expiration markers and cardiac related variables. Cough and apnea detection, adventitious sound recognition, activities performed, and information about energy estimation and the status of a monitored subject can be derived as well.